© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 92480
    Prev
    Next
    INDEX
    Explanations

    "um" sound followed by specific suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    oric
    -0.08
     Rover
    -0.08
    IRD
    -0.08
     Cann
    -0.08
     Singer
    -0.08
    oref
    -0.07
     disin
    -0.07
     Pang
    -0.07
     ine
    -0.07
     Champion
    -0.07
    POSITIVE LOGITS
    washer
    0.11
    ded
    0.11
    mock
    0.11
    dden
    0.11
    },"
    0.11
     crumbs
    0.11
     tutorial
    0.10
     sack
    0.10
     cigaret
    0.10
    edException
    0.10
    Activations Density 0.002%

    No Known Activations